Docstoc

Transformational idea from Google

Document Sample
Transformational idea from Google Powered By Docstoc
					Transformational idea from Google: voice recognize

Once upon a time, there are some idea that computers can show you the data’s or information
just through your voice, but it’s only exists in science fiction. Now, Google try to manifest the
notion to its search engine, and allow any browser, web, applications to use the feature.

The big question mark that you must consider in your calculation is: are you ready to talk or
make some loud with Google? It means that you have to stop typing in keyboard ungrudgingly.

A couple weeks ago, speech input in Google has regularly been applied to Google’s Chrome
Browser. This implementation is proven with a microphone icon that emerges at the right end of
the search box. If you have an integrated or external microphone, just click the icon and make
some speech, it connect your voice to Google’s server, which the machine will convert your
verbal into text.

In the other hand, speak to Google using a smart phone it was happened in three years, last year
Android handsets have been able to take voice in any circumstances while a keyboard would
normally be used. . ―That was radical idea, because people stopped worrying about when they
could and couldn’t speak to the phone,‖ says Vincent Vanhoucke , who frontrunners the voice
search engineering team at Google lab. Over the twelve months, the quantity of spoken inout, via
android smartphone increase six times than before, and every single day, 10.000 hours of audio
speech provided for Google’s servers. ―On Android, a large segment of the use that is people
who want to verbalize their e-mail and Short Massage Service,‖ says Vanhoucke.

Now, Vanhoucke’s team wants to use voice on the Web to be as easy as Android do. ―It’s a big
bet,‖ he says. ―Voice search for desktop is the Leader for this, [but] we want to take speech
everywhere.‖

Voice recognition is more theoretically challenging on a desktop or laptop, says Vanhoucke,
because it needs noise suppression algorithms that are not needed for mobile speech recognition.
These algorithms can filter out the sounds for example those of a computer’s fan or air
conditioners. ―The quality of the audio is principal for phone manufacturers, and you hold it
close to your mouth,‖ says Vanhoucke. ―On a Personal Computer, the microphone is an addition,
and you are further away. You don’t get the best quality.‖

Google asked a lot of people to saying some words or phrases loudly to their computers to
collect data on the circumstances its speech recognition technology would handle it. As people
use the service for real, it is trained further, says Vanhoucke, which should increase its
popularity. Data from users of mobile voice search shows that people are much more likely to
use the feature twice or more when it is accurate for them the first time.

A higher challenge to getting users to power on voice recognition on the desktop could be the
existing tools for entering information, says Keith Vertanen, a researches and lecturer at
Princeton University voice-recognition technology. ―On the desktop, you’re up against a very
fast and efficient means of input in the keyboard,‖ he says. ―On a phone, you don’t have that
available, and you are often in hands- or eyes-free situations where voice input really helps.‖
Vertanen says people are less tolerant of glitches when using speech recognition on a desktop
computer because of they have pre-experience of tried-and-true way of entering text. He said that
the client might find voice recognition more convincing on other Internet-connected devices.
―Production of nonconventional devices like a television, DVR, or game console usually don’t
include the good text input,‖ he speak loud. Google TV devices have this feature and already
connected with Android phone.

Vanhoucke hold true that speech recognition achieves is more immediate need on mobile
phones, but argues that users are ready for it on conventional computers, too. ―People will use it
in ways that surprise us,‖ he says. ―At this point, it’s still experimentation.‖ The State when
people may have their hands full is one example, says Vanhoucke (you have to consider if you
want to use the voice recognition on PC, you have to move the mouse cursor and click the icon
don’t you?)
Google isn’t execution this experiment alone. The company collaborated with the Web standards
body W3C to introduce a standard set of HTML markup that allows any website or app to make
call on voice recognition via the Web browser, and it already in the Google’s Chrome browser.
Currently, Only Google with its Chrome browser able to use the prototype feature. Mozilla,
Microsoft, and AT&T are all working with the W3C work.

―It’s a collaborative effort that other browser makers are part of,‖ says Vanhoucke. ―Any
designer can add it to their Web page. It’s something anyone can use.‖ Extensions for the
Chrome browser that make use of voice input (like this one) have already appeared, and can be
used to enter text on any website.

However, those plugins make known that although Google’s desktop speech recognition is
accurate for search queries, it’s far away from good for tasks like composing e-mail.

Enabling the system to learn the personal idiosyncrasies of each person’s pronunciation, the
feature has been enabled on Android phones, could address that. Vertanen speak loud that the
personalization learned through mobile search could easily be connected over to the desktop for
people logged into their Google account. It could also make it possible for the technology to
develop elsewhere. ―The advantage of Google’s networked approach is that a [speech] model in
the cloud –you can make voice on different place—whether in your living room or in your office
and it can follow you around.

				
DOCUMENT INFO
Shared By:
Stats:
views:18
posted:7/16/2011
language:English
pages:2